An algorithm effects a causal representation of relations between features and labels in the human's perception. Such a representation might conflict with the human's prior belief. Explanations can direct the human's attention to the conflicting feature and away from other relevant features. This leads to causal overattribution and may adversely affect the human's information processing. In a field experiment we implemented an XGBoost-trained model as a decision-making aid for counselors at a public employment service to predict candidates' risk of long-term unemployment. The treatment group of counselors was also provided with SHAP. The results show that the quality of the human's decision-making is worse when a feature on which the human holds a conflicting prior belief is displayed as part of the explanation.
Decisions in organizations are about evaluating alternatives and choosing the one that would best serve organizational goals. To the extent that the evaluation of alternatives could be formulated as a predictive task with appropriate metrics, machine learning algorithms are increasingly being used to improve the efficiency of the process. Explanations help to facilitate communication between the algorithm and the human decision-maker, making it easier for the latter to interpret and make decisions on the basis of predictions by the former. Feature-based explanations' semantics of causal models, however, induce leakage from the decision-maker's prior beliefs. Our findings from a field experiment demonstrate empirically how this leads to confirmation bias and disparate impact on the decision-maker's confidence in the predictions. Such differences can lead to sub-optimal and biased decision outcomes.